{"id":"https://openalex.org/W4389111296","doi":"https://doi.org/10.1145/3630048.3630187","title":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","display_name":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","publication_year":2023,"publication_date":"2023-11-28","ids":{"openalex":"https://openalex.org/W4389111296","doi":"https://doi.org/10.1145/3630048.3630187"},"language":"en","primary_location":{"id":"doi:10.1145/3630048.3630187","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630048.3630187","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630048.3630187","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Distributed Machine Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630048.3630187","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026967025","display_name":"Grigory Malinovsky","orcid":"https://orcid.org/0000-0001-6428-1866"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Grigory Malinovsky","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-6428-1866","affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015808280","display_name":"Konstantin Mishchenko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Konstantin Mishchenko","raw_affiliation_strings":["Samsung AI Center, Cambridge, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-5241-7292","affiliations":[{"raw_affiliation_string":"Samsung AI Center, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036598221","display_name":"Peter Richt\u00e1rik","orcid":"https://orcid.org/0000-0003-4380-5848"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Peter Richt\u00e1rik","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-4380-5848","affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78898439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795429825782776},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6904465556144714},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5530883073806763},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5383051633834839},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.47788894176483154},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4509264826774597},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.41691672801971436},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.3927575349807739},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3893596827983856},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32163912057876587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1319466233253479},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10767263174057007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795429825782776},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6904465556144714},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5530883073806763},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5383051633834839},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47788894176483154},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4509264826774597},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.41691672801971436},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3927575349807739},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3893596827983856},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32163912057876587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1319466233253479},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10767263174057007},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630048.3630187","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630048.3630187","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630048.3630187","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Distributed Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3630048.3630187","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630048.3630187","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630048.3630187","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Distributed Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389111296.pdf","grobid_xml":"https://content.openalex.org/works/W4389111296.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1576278180","https://openalex.org/W2153635508","https://openalex.org/W2913668833","https://openalex.org/W2990138404","https://openalex.org/W3034797957","https://openalex.org/W4287328069"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W2411838016","https://openalex.org/W3153752017"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,61,99,146,170,208,224],"theoretical":[3],"study":[4],"of":[5,23,38,125,128,162,177,201,214,226],"server-side":[6,172,205,216],"optimization":[7,217],"in":[8,35,88,102,118,218],"federated":[9,219],"learning.":[10,220],"Our":[11],"results":[12,197],"are":[13,78,155],"the":[14,19,25,36,46,75,81,103,126,152,160,175,182,192,199,212,236],"first":[15,183],"to":[16,133,190],"show":[17,66],"that":[18,73,159,185,229],"widely":[20],"popular":[21],"heuristic":[22],"scaling":[24],"client":[26,47,163,232],"updates":[27],"with":[28,42,90],"an":[29,123],"extra":[30],"parameter":[31],"is":[32,52,60,84,138,181],"very":[33],"useful":[34],"context":[37],"Federated":[39],"Averaging":[40],"(FedAvg)":[41],"local":[43,50,76,153,186],"passes":[44],"over":[45,93],"data.":[48],"Each":[49],"pass":[51],"performed":[53,144],"without":[54],"replacement":[55],"using":[56,169],"Random":[57,91,142],"Reshuffling,":[58],"which":[59,234],"key":[62],"reason":[63],"we":[64,71,121,157,222],"can":[65,97,165],"improved":[67],"complexities.":[68],"In":[69,116,149],"particular,":[70,117],"prove":[72,158],"whenever":[74],"stepsizes":[77,154,206],"small,":[79],"and":[80,106,113,203],"update":[82],"direction":[83,105],"given":[85],"by":[86,168],"FedAvg":[87],"conjunction":[89],"Reshuffling":[92,143],"all":[94],"clients,":[95],"one":[96],"take":[98],"big":[100],"leap":[101],"obtained":[104],"improve":[107],"rates":[108],"for":[109,141,211],"convex,":[110,112],"strongly":[111],"non-convex":[114,119],"objectives.":[115],"regime":[120],"get":[122],"enhancement":[124],"rate":[127],"convergence":[129],"from":[130],"<scr>O</scr>":[131,134],"(\u03b5\u22123)":[132],"(\u03b5\u22122).":[135],"This":[136],"result":[137],"new":[139],"even":[140],"on":[145,198],"single":[147],"node.":[148],"contrast,":[150],"if":[151],"large,":[156],"noise":[161],"sampling":[164],"be":[166],"controlled":[167],"small":[171,204],"stepsize.":[173],"To":[174],"best":[176],"our":[178,196,227],"knowledge,":[179],"this":[180],"time":[184],"steps":[187],"provably":[188],"help":[189],"overcome":[191],"communication":[193],"bottleneck.":[194],"Together,":[195],"advantage":[200],"large":[202],"give":[207],"formal":[209],"justification":[210],"practice":[213],"adaptive":[215],"Moreover,":[221],"consider":[223],"variant":[225],"algorithm":[228],"supports":[230],"partial":[231],"participation,":[233],"makes":[235],"method":[237],"more":[238],"practical.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}